公开(公告)号：WO2021206408A1

公开(公告)日：2021-10-14

申请号：PCT/KR2021/004256

申请日：2021-04-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： CHEN, Winston ,  GOMBOS, Laszlo

IPC: G06F3/0483 ,  G06F3/01 ,  G06F3/0481 ,  G06F3/0482 ,  G06F16/958 ,  G06F16/953 ,  G06F16/954 ,  G06F9/451

Abstract: A method includes retrieving a webpage requested by an extended reality (XR) web reader. The method further includes determining one or more content elements of the webpage and one or more menu elements of the webpage. The menu elements may comprise navigational controls for accessing additional content linked to the webpage. The method further includes mapping the one or more menu elements to one or more pre-defined menu interfaces of the XR web reader. The method further includes presenting the webpage via the XR web reader. The one or more content elements may be presented on one or more first layers of an interface of the XR web reader, and the one or more pre-defined menu interfaces may be presented on one or more second layers of the interface of the XR web reader.

公开(公告)号：WO2021174699A1

公开(公告)日：2021-09-10

申请号：PCT/CN2020/093424

申请日：2020-05-29

Applicant: 平安科技（深圳）有限公司

Inventor： 余雯 ,  黄承伟

IPC: H04L29/06 ,  G06F16/953

Abstract: 本申请涉及人工智能中的数据分析领域，公开了一种用户筛选方法、装置、设备及存储介质，所述方法包括：获取待识别用户的线下图像数据和线上数据，所述线下图像数据包括拜访记录图像；对所述拜访记录图像进行图像处理，以得到所述待识别用户的线下拜访数据；将所述线下拜访数据和线上数据作为所述待识别用户的基础数据，并对所述基础数据进行特征衍生以得到所述待识别用户的特征数据；根据预先训练的用户识别模型对所述待识别用户的特征数据进行特征因子匹配；当所述待识别用户的特征数据与所述用户识别模型中的特征因子的匹配度满足预设条件时，确定所述待识别用户为目标用户。提高从新用户中筛选出目标用户的准确率。

公开(公告)号：WO2021120627A1

公开(公告)日：2021-06-24

申请号：PCT/CN2020/105007

申请日：2020-07-28

Applicant: 深圳壹账通智能科技有限公司

Inventor： 董润华 ,  徐国强

IPC: G06F16/36 ,  G06F16/367 ,  G06F16/953

Abstract: 一种数据搜索匹配方法、装置、计算机设备和计算机可读存储介质，涉及大数据技术领域中的数据挖掘，数据搜索匹配方法包括：获取待搜索的关键词以及关键词对应的事件图谱；根据事件图谱中各节点之间的关系，计算关键词在事件图谱中所属节点与事件图谱中其它节点之间的距离，提取距离小于第一预设阈值的节点，获得第一拓展关键词；根据目标百科图谱中各节点之间的关系，计算关键词在目标百科图谱中所属节点与目标百科图谱中其它节点之间的距离，提取距离小于第二预设阈值的节点，获得第二拓展关键词；将关键词、第一拓展关键词以及第二拓展关键词合并，获得关键词集合，基于关键词集合以及预设的搜索与分析引擎进行搜索，获得搜索结果。

公开(公告)号：WO2021012522A1

公开(公告)日：2021-01-28

申请号：PCT/CN2019/118149

申请日：2019-11-13

Applicant: 平安科技(深圳)有限公司

Inventor： 陈爽 ,  陈源

IPC: G06F16/953 ,  G06K9/00

Abstract: 一种基于图像识别的网页取证方法、装置、计算机非易失性可读存储介质及服务器，方法包括：接收终端设备发送的网页取证请求（S101），所述网页取证请求中包括目标网页的统一资源定位符和目标图像；从所述网页取证请求中提取出所述统一资源定位符，并根据所述统一资源定位符获取所述目标网页（S102）；从所述目标网页中选取动态元素对象（S103），并采集所述动态元素对象的图像序列（S104）；从所述网页取证请求中提取出所述目标图像，并分别计算所述图像序列的各帧图像与所述目标图像之间的相似度（S105）；从所述图像序列的各帧图像中选取出证据图像（S106），所述证件图像为与所述目标图像之间的相似度大于预设的相似度阈值的一帧图像。由于对证据图像的取证过程是由取证服务器完成，大大提升了该证据的信服力，从而可以在诉讼过程中被法庭所接受。

公开(公告)号：WO2020263228A1

公开(公告)日：2020-12-30

申请号：PCT/US2019/038940

申请日：2019-06-25

Applicant: GOOGLE LLC

Inventor： CARBUNE, Victor ,  FEUZ, Sandro

IPC: G06N5/02 ,  G06F40/205 ,  G06F40/35 ,  G06F16/95 ,  G06F3/16 ,  G06F16/901 ,  G06Q50/00 ,  G06F16/953 ,  G06N3/04 ,  G06N3/08 ,  G06N7/00

Abstract: Techniques and a framework are described herein for constructing and/or updating, e.g. , on top of a general-purpose knowledge graph, an "event-specific provisional knowledge graph." In various implementations, live data stream(s) may be analyzed to identify entity(s) associated with a developing event. The entity(s) may form part of a general-purpose knowledge graph that includes entity nodes and edges between the entity nodes. Based on the identified one or more entities, an event-specific provisional knowledge graph may be constructed or updated in association with the developing event. In some implementations, the event-specific provisional knowledge graph may be queried for new information about the developing event. Computing devices may be caused to render, as output, the new information.

公开(公告)号：WO2020256827A1

公开(公告)日：2020-12-24

申请号：PCT/US2020/030003

申请日：2020-04-26

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： WU, Xiaojian ,  CHAKRABORTY, Doran ,  SEO, Hyun-Ju ,  LIN, Sina ,  VENKATASUBRAMANIAN, Gangadharan

IPC: G06F16/953 ,  G06N3/04

Abstract: Various technologies relating to constructing an answer to a query are described herein, wherein the answer is in list form. The answer includes a header and a list element. A deep model receives content of a webpage that is deemed relevant to the query by a search engine and constructs the answer to the webpage upon receipt of the query.

公开(公告)号：WO2020235724A1

公开(公告)日：2020-11-26

申请号：PCT/KR2019/006188

申请日：2019-05-23

Applicant: 엘지전자 주식회사

Inventor： 이기웅

IPC: G06F16/783 ,  G06F16/953 ,  G06F3/0481 ,  H04N21/422 ,  H04N21/431 ,  H04N21/462

Abstract: 본 발명은 등장 인물 검색 요청을 수신시 현재 장면 속 인물에 대한 정보를 사용자에게 보다 용이하게 제공할 수 있는 디스플레이 장치에 관한 것으로, 영상을 표시하는 디스플레이부, 영상과 관련된 등장 인물들의 인물 정보를 수신하는 무선 통신부 및 인물 정보에 기초하여 등장 인물들의 썸네일 표시하도록 디스플레이부를 제어하는 제어부를 포함하고, 제어부는 등장 인물들의 썸네일 중 현재 장면 속 인물의 얼굴 이미지와 가장 유사한 매칭 인물의 썸네일에 인디케이터를 표시하도록 디스플레이부를 제어할 수 있다.

公开(公告)号：WO2020155496A1

公开(公告)日：2020-08-06

申请号：PCT/CN2019/089609

申请日：2019-05-31

Applicant: 平安科技(深圳)有限公司

Inventor： 吴壮伟

IPC: G06F16/953 ,  G06F16/73

Abstract: 本申请提供一种视频文本组合数据的舆情跟踪方法、装置和计算机设备，方法包括：获取指定公开数据，构建公开数据库；在公开数据库中筛选舆情话题对应的舆情视频文本组合数据、舆情文本数据、舆情视频数据；结合所有筛选数据形成舆情数据。本申请通过将舆情信息中的文本和视频相结合进行跟踪，实现对舆情信息的全面跟踪。

公开(公告)号：WO2020128606A1

公开(公告)日：2020-06-25

申请号：PCT/IB2019/001297

申请日：2019-12-10

Applicant: SINCHEV, Bakhtgerey ,  SINCHEV, Askar ,  AKZHANOVA, Zhanna ,  ISSEKESHEV, Yerlan

Inventor： SINCHEV, Bakhtgerey ,  SINCHEV, Askar ,  AKZHANOVA, Zhanna ,  ISSEKESHEV, Yerlan

IPC: G06F9/30 ,  G06F16/901 ,  G06F16/953

Abstract: This disclosure is directed to reducing a computing operation time and reducing memory usage associated with determining at least two target data elements, associated with a target computing operation result, from a set of data elements. This disclosure can be extended to determining more than two target data elements, associated with a target computing operation result, from a set of data elements, as well.

公开(公告)号：WO2020082404A1

公开(公告)日：2020-04-30

申请号：PCT/CN2018/112895

申请日：2018-10-31

Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.

Inventor： HU, Juan ,  CHEN, Huan ,  SONG, Qi ,  MA, Li

IPC: G06F16/9537 ,  G06F16/953 ,  G06F16/9538 ,  G06F16/9535

Abstract: The present disclosure relates to systems and methods for recalling one or more POIs. The systems and methods may receive a query inputted by a user via a terminal and determine one or more terms by processing the received query. The systems and methods may further label the one or more terms using a trained tagging model. The systems and methods may determine one or more POIs based on the labeled one or more terms, and display the one or more terms on the terminal.